© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15114
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem identification and solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -1.00
     CURLOPT
    -0.96
     définiti
    -0.89
     تضيفلها
    -0.87
     vectorielles
    -0.83
     recevez
    -0.82
     témo
    -0.79
     tawny
    -0.78
     désigne
    -0.78
     étoit
    -0.77
    POSITIVE LOGITS
     problems
    1.80
     problem
    1.74
     Problem
    1.62
     Problems
    1.62
     PROBLEM
    1.51
    Problems
    1.50
    Problem
    1.45
    problems
    1.43
    problem
    1.42
    PROBLEM
    1.41
    Activations Density 0.107%

    No Known Activations